© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15867
    Prev
    Next
    INDEX
    Explanations

    specific items or numbers

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects discourse-level emphasis or transition words (e.g. adverbial cues and sentence-starting markers like “especially,” “Make,” “reclaimed,” “Humanities,” “not,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Mozilla
    0.84
    
    0.83
    कायदा
    0.82
    드가
    0.80
    គ្មាន
    0.79
     vardı
    0.79
    Sew
    0.79
    鐧
    0.78
    老
    0.77
     कायदा
    0.77
    POSITIVE LOGITS
     อัน
    0.68
     rect
    0.68
     Emit
    0.66
    ebut
    0.66
     raid
    0.65
     jockey
    0.65
    ُم
    0.64
     pony
    0.64
     interv
    0.64
     Nota
    0.64
    Activations Density 0.000%

    No Known Activations